mediumMultiple Choice
PDE Practice Question: A retail company uses a Vertex AI endpoint to…
A retail company uses a Vertex AI endpoint to serve product recommendations. The model is a TensorFlow model deployed with a custom container. Recently, users have reported that recommendations are stale. The model is retrained daily using Vertex AI Pipelines. The pipeline completes successfully, but the endpoint continues to serve the old model. The team checks the pipeline logs and sees that the new model is uploaded to the Vertex AI Model Registry. The endpoint has traffic split set to 100% for the old model. The team needs to update the endpoint to serve the new model version. What should they do?
⚠ Common exam trap
Google Cloud often tests the misconception that uploading a new model version to the registry automatically updates the endpoint's serving configuration, when in fact the traffic split must be explicitly adjusted to route requests to the new model.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Update the endpoint to deploy the new model version from the registry and adjust traffic split
The pipeline successfully uploaded the new model to the Vertex AI Model Registry, but the endpoint still has its traffic split configured to 100% for the old model. To serve the new model, the team must explicitly update the endpoint to deploy the new model version from the registry and adjust the traffic split to route 100% of traffic to it. This is a standard operational step in Vertex AI: uploading a model does not automatically update the endpoint's deployment or traffic allocation.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Check the pipeline for errors in the deployment step
Why it's wrong here
The pipeline completes successfully and the model reaches the Model Registry, so no deployment-step error exists to find. Checking logs is tempting because pipelines normally deploy models, but here the endpoint's traffic split still points 100% at the old version, which must be changed directly.
- ✗
Re-upload the model with a different version ID
Why it's wrong here
Re-uploading with a different version ID does not alter the endpoint's traffic split, which still routes 100% to the old model. Versioning is tempting because it tracks model lineage in the Model Registry, but the correct choice is to update the endpoint's deployed model and traffic allocation.
- ✗
Redeploy the same model to the endpoint
Why it's wrong here
Redeploying the same model leaves the endpoint serving the identical old version, so recommendations stay stale. Redeployment is tempting because it refreshes an endpoint, but the new model already exists in the Model Registry; the endpoint must be pointed at that new version instead.
- ✓
Update the endpoint to deploy the new model version from the registry and adjust traffic split
Why this is correct
The endpoint still routes 100% of traffic to the old model, so uploading to the registry alone changes nothing. Deploying the new version to the endpoint and shifting the traffic split directs live inference to it.
Go deeper
Related to this question
About these practice questions
Courseiva writes every PDE question from scratch — 747 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PDE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PDE exam.